Skills

Bridge the vercel-labs/skills ecosystem into dsh: LLM-driven skill search, install, and lifecycle for temp/project/global scopes

Global skill hub for dsh: aggregates Claude Code, project, and .skill-package skills into ~/.dsh/skills with reference/copy import and slash-menu usage

Structured code review skill for DeepSeek Harness -- bugs, security, performance, style

面向非开发人员的 35 个技能 bundle（DSH profile bundle，非 Agent 预设）：编排 + 工程 + 产品 + 界面/上线。dsh plugin add coding-coach 即可把技能装进任意 profile；完整「编程教练」Agent 见仓库 dsh/coding-coach 目录。

Design I/O for coding agents: controllable UI generation via declarations (spec/domain/craft/design/components/template) and contracts (skill/evaluator). Use for product UI—console, dashboard, agent-ops, CJK-first apps.

Auto-inject user-chosen skills (e.g. caveman, ponytail) into DeepSeek Harness sessions.every prompt or once at session start.

Skill manager for DSH: drag rows into the order you want, pin any row straight to position 1, and rename a skill inline. Applying rewrites each directory name and the name field in SKILL.md. A skill that appears later is numbered and cleaned up automatically, and a description past 20 Chinese characters gets rewritten. Every change clears the host skill cache and notifies each session, so the slash menu follows at once without restarting DSH. Local-only and offline. Its HTTP routes have no DSH access check, so a page open in your browser could trigger a rename or reorder of your skill folders.

Lazy senior coding ruleset for DeepSeek Harness: injects minimal-code guidance, adds review, audit, debt, gain and help skills, and switches lite/full/ultra per session. Ships a script to sync rules from a pinned upstream commit.

Captures verified project work as masked evidence and reviewable skill proposals; accepted skills become native project skills with version history, diff, rollback, and opt-in global publishing.

Shows and loads Qwen (qianwen*) skills only when the session runs on the Qwen Token Plan CN provider, and hides and blocks them on any other provider.

Registers 36 bundled agent skills (research writing, LaTeX, experiments, design review, office documents, animation, Windows shell and dsh plugin conventions) as one host-only skill provider with no UI, no network calls and no telemetry of its own; skill scripts run with the user's permissions only when invoked, local skills of the same name take priority, and uninstall removes all 36.

Bundles the stack-diagram architecture-diagram skill as a runtime skill, and injects a system-prompt section so the model draws diagrams without being asked. Output is self-contained HTML plus light and dark PNGs from bundled Python scripts; brand logos are fetched at run time.

Registers a skill that turns a Bilibili video link into a structured Obsidian note. It fetches subtitles only with yt-dlp and never downloads the video, merges multi-part anthologies onto one continuous timeline, and writes front matter, timestamped jump-link bullets, a summary and tags into the vault.

Registers 25 software engineering workflow skills covering spec, planning, build, test, review and ship. Mirrored from addyosmani/agent-skills (MIT).

Browses and edits the skills directory in a VSCode-style file tree and editor panel in the DSH web client sidebar: creates, renames and deletes files and directories, reads and saves text files under size caps, and switches the served root directory from the panel (persisted through the profile config editor).

Turns the QQ groups you follow into a Chinese daily digest. Pulls chat history through a local NapCat/OneBot 11 service into SQLite, summarizes each group, and renders an HTML/Markdown report with an opportunity radar that surfaces repeated complaints, tool requests and unmet needs as product ideas; can push a card to Feishu on a schedule.

Skill that transcribes local audio files into a timestamped transcript and an interactive two-column minutes page, with optional speaker separation. Transcription uses mlx-whisper in a Python 3.11 environment you set up yourself (the first run may download models); the renderer uses only the system python3. Given a public short-video share link, it can also drive a real browser through ego-browser and fetch the audio track with curl and ffmpeg, none of which ship with the package.

A lazy-mode plugin for DeepSeek Harness: mode-graded decision guidance, fence-aware prompt filtering and a two-language skill catalog.

Document-form plan task-book plugin for DeepSeek Harness: one entry skill plus three tools — structure check, skeleton generator, package self-check — for a four-element task book, with the protocol reference shipped in-package. Only the generator writes files, and it refuses to overwrite an existing one unless force is set.

Agent skills for Obsidian, vendored verbatim from the official repository kepano/obsidian-skills (MIT, Steph Ango). Six skills covering Obsidian Flavored Markdown (wikilinks, embeds, callouts, properties), Bases (.base), JSON Canvas (.canvas), the Obsidian CLI, Defuddle and Knap. Documentation only: no CLI binaries are bundled, so obsidian/defuddle/knap are installed separately by the user.

Skill usage history rebuilt from local session logs, with per-day counts, session drill-down and custom groups.

Skill quick-pick panel for the composer: lists the session's skills by source, inserts /name into the draft without sending it, and can disable, uninstall or track usage per skill. Disabling skills (rewrites SKILL.md), uninstalling them (moves the folder to a trash), usage statistics (reads local session logs) and model translation of skill names are all off by default and switched on one by one in the panel settings.

Health check for a DSH profile: scores skills and agent instruction files, subagent definitions and presets on one shared 18-bucket S–E grade scale, with a sidebar panel, four dsh360_* tools, and a backup with undo for every write.

Find photo candidates from the 2026 Qiandao Lake cycling race by bib number and visible gear, with local helper scripts and album snapshot comparison. Needs the event's photo album link; snapshot comparison uses Python 3.10+, bib OCR is macOS only (Swift and Apple Vision), and the optional gear ranking needs Pillow, PyTorch, Transformers and a local DINOv2 model directory.